INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     immutable
    -0.08
     Evangel
    -0.08
    ژ
    -0.07
    ڑا
    -0.07
    immutable
    -0.07
    -0.07
     Subscriber
    -0.07
     subscribed
    -0.07
    etet
    -0.07
    ceed
    -0.07
    POSITIVE LOGITS
     rust
    0.09
     가족
    0.09
    Tunnel
    0.09
     dangers
    0.09
     confin
    0.09
     burglar
    0.09
     ഫെ
    0.08
     wię
    0.08
     burgl
    0.08
     trag
    0.08
    Act Density 0.002%

    No Known Activations